© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 125347
    Prev
    Next
    INDEX
    Explanations

    ATM and locations

    np_acts-logits-general · gemini-2.5-flash-lite

    She intelligent / makes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    0.52
    ^
    0.49
    -
    0.46
    wn
    0.45
    =”
    0.45
     ดัง
    0.45
    =""
    0.43
     pretreatment
    0.43
    )
    0.42
     u
    0.42
    POSITIVE LOGITS
    ၟ
    0.56
    ِمض
    0.54
     politici
    0.52
    政治
    0.52
     actifs
    0.51
    DAMAGE
    0.51
    ፖ
    0.51
     politischen
    0.51
     LIM
    0.50
     ஏற்கனவே
    0.50
    Activations Density 0.001%

    No Known Activations